floodsung / Learningtocompare_fsl
Licence: mit
PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)
Stars: ✭ 837
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Learningtocompare fsl
rl implementations
No description or website provided.
Stars: ✭ 40 (-95.22%)
Mutual labels: meta-learning
Matchingnetworks
This repo provides pytorch code which replicates the results of the Matching Networks for One Shot Learning paper on the Omniglot and MiniImageNet dataset
Stars: ✭ 256 (-69.41%)
Mutual labels: meta-learning
Meta Dataset
A dataset of datasets for learning to learn from few examples
Stars: ✭ 483 (-42.29%)
Mutual labels: meta-learning
CDFSL-ATA
[IJCAI 2021] Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
Stars: ✭ 21 (-97.49%)
Mutual labels: meta-learning
Meta-SAC
Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient - 7th ICML AutoML workshop 2020
Stars: ✭ 19 (-97.73%)
Mutual labels: meta-learning
Metaoptnet
Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
Stars: ✭ 412 (-50.78%)
Mutual labels: meta-learning
maml-rl-tf2
Implementation of Model-Agnostic Meta-Learning (MAML) applied on Reinforcement Learning problems in TensorFlow 2.
Stars: ✭ 16 (-98.09%)
Mutual labels: meta-learning
Awesome Automl And Lightweight Models
A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
Stars: ✭ 691 (-17.44%)
Mutual labels: meta-learning
e-osvos
Implementation of "Make One-Shot Video Object Segmentation Efficient Again” and the semi-supervised fine-tuning "e-OSVOS" approach (NeurIPS 2020).
Stars: ✭ 31 (-96.3%)
Mutual labels: meta-learning
Awesome Papers Fewshot
Collection for Few-shot Learning
Stars: ✭ 466 (-44.32%)
Mutual labels: meta-learning
dropclass speaker
DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020
Stars: ✭ 20 (-97.61%)
Mutual labels: meta-learning
resilient-swarm-communications-with-meta-graph-convolutional-networks
Meta graph convolutional neural network-assisted resilient swarm communications
Stars: ✭ 49 (-94.15%)
Mutual labels: meta-learning
Meta Transfer Learning
TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)
Stars: ✭ 439 (-47.55%)
Mutual labels: meta-learning
PAML
Personalizing Dialogue Agents via Meta-Learning
Stars: ✭ 114 (-86.38%)
Mutual labels: meta-learning
Cfnet
[CVPR'17] Training a Correlation Filter end-to-end allows lightweight networks of 2 layers (600 kB) to high performance at fast speed..
Stars: ✭ 496 (-40.74%)
Mutual labels: meta-learning
Open-L2O
Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms
Stars: ✭ 108 (-87.1%)
Mutual labels: meta-learning
Multitask Learning
Awesome Multitask Learning Resources
Stars: ✭ 361 (-56.87%)
Mutual labels: meta-learning
Few Shot
Repository for few-shot learning machine learning projects
Stars: ✭ 727 (-13.14%)
Mutual labels: meta-learning
Auto Sklearn
Automated Machine Learning with scikit-learn
Stars: ✭ 5,916 (+606.81%)
Mutual labels: meta-learning
Reinforcement learning tutorial with demo
Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..
Stars: ✭ 442 (-47.19%)
Mutual labels: meta-learning
LearningToCompare_FSL
PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)
For Zero-Shot Learning part, please visit here.
Requirements
Python 2.7
Pytorch 0.3
Data
For Omniglot experiments, I directly attach omniglot 28x28 resized images in the git, which is created based on omniglot and maml.
For mini-Imagenet experiments, please download mini-Imagenet and put it in ./datas/mini-Imagenet and run proc_image.py to preprocess generate train/val/test datasets. (This process method is based on maml).
Train
omniglot 5way 1 shot:
python omniglot_train_one_shot.py -w 5 -s 1 -b 19
omniglot 5way 5 shot:
python omniglot_train_few_shot.py -w 5 -s 5 -b 15
omniglot 20way 1 shot:
python omniglot_train_one_shot.py -w 20 -s 1 -b 10
omniglot 20way 5 shot:
python omniglot_train_few_shot.py -w 20 -s 5 -b 5
mini-Imagenet 5 way 1 shot:
python miniimagenet_train_one_shot.py -w 5 -s 1 -b 15
mini-Imagenet 5 way 5 shot:
python miniimagenet_train_few_shot.py -w 5 -s 5 -b 10
you can change -b parameter based on your GPU memory. Currently It will load my trained model, if you want to train from scratch, you can delete models by yourself.
Test
omniglot 5way 1 shot:
python omniglot_test_one_shot.py -w 5 -s 1
Other experiments' testings are similar.
Citing
If you use this code in your research, please use the following BibTeX entry.
@inproceedings{sung2018learning,
title={Learning to Compare: Relation Network for Few-Shot Learning},
author={Sung, Flood and Yang, Yongxin and Zhang, Li and Xiang, Tao and Torr, Philip HS and Hospedales, Timothy M},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2018}
}
Reference
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].